Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 5 of 5 for “"Vision neuroscience"”.
-
Recurrent neural networks in cognitive and vision neuroscience
This thesis investigates the development of novel training methodologies for biologically plausible neural networks, with a focus on models that incorporate recurrent dynamics characteristic of cortical circuits. First, we present an innovative approach for training stabilized supralinear networks, …
-
Light Dance: Beyond the Dichotomy of Light and Vision
… Light Dance: Beyond the Dichotomy of Light and Vision Seth Riskin This practice-based dissertation focuses on Light Dance, an original artistic practice developed by the author that, in reducing light to its core elements in a setting devoid of other sources of illumination, centers the …
-
Dictionary learning for scalable sparse image representation
… from experimental sciences, astronomy, computer vision,neuroscience mobile networks etc., are all in constant search for scalable and efficient data processing tools which would enable more effective analysis of continuous video streams containing millions of pixels. Therefore, the question of …
-
Recurrent convolutional neural networks as models of biological object recognition
Deep feedforward neural network models of vision dominate in both computational neuroscience and engineering. However, the primate visual system contains abundant recurrent connections. In this thesis, we investigate the addition of recurrent connections to the popular framework of convolutional …
-
High-Throughput Operant Conditioning in Drosophila Larvae
Operant conditioning is the process by which animals learn to associate their own behaviour with positive or negative outcomes, biasing future action selection in order to maximise reward and avoid punishment. It is an important strategy to ensure survival in an ever-changing environment. Although …